Model evaluation for rsds

• Climate variables used as response: - sfcWind, tas, pr: original scale daily, reduced scale: hourly - clt, rsds: original scale monthly, reduced scale: daily

• Training: All models are trained using ERA5 in reduced scale as observations. Training data perdiod: 1980 - 2015.

• Validation Period: 2015-01-29 to 2023-12-03

• Response variable to predict: upscaled ERA5 (daily or monthly)

• Predictors variables: daily scale the variables sfcWind, tas, pr, tasmax, tasmin and psl and in a monthly scale clt, rsdt,rsds , the month and the daily daylight amount in seconds.

Numerical evaluation metrics

• Each row correspond an evaluation metric
• Dark blue cell indicates the best model in the row.
• Light blue cell indicates the second best model in the row.

Metric	xgboost	cnn	naive	lstm
mae	16.59	20.87	23.54	19.07
cor	0.97	0.95	0.94	0.96
ratio_of_sd	0.96	0.95	0.94	0.97
KGE	0.95	0.93	0.92	0.95
amplitude_mae_monthly	22.37	20.12	32.49	21.40
sign_correlation	0.81	0.75	0.74	0.78
extreme_correlation	1.00	0.77	0.78	0.92
qqplot_mae	3.30	4.71	7.13	2.68
acf_mae	0.05	0.04	0.06	0.04
extremogram_mae	0.02	0.04	0.03	0.03

Graphical evaluation metrics

• Observations: cumulative distribution (Detrended QQ), dependency structure (ACF), and extremes (Extremogram, using 0.97 cut off).

• Daily/Monthly gruped: Maximum hour histogram (only in daily variables), Amplitude distribution.

• Hourly/Daily grouped: Mean profile per hour within days (or weeks witihin season)

• In all plots, grey color represent the true ERA5 signal.